Dzetsaka, classification plugin, is now available on Qgis 3

Thanks to the amazing work of Qgis 3 contributors, Qgis 3 is now here and it’s awesome !

I manage to have a few days free to migrate dzetsaka to python 3 and to PyQt5, so dzetsaka is now available on the plugin repository.

Not every functions have been implemented, but major ones are here and the processing toolbox is now way more efficient. I quite recommend you to use dzetsaka from the processing toolbox than for the user interface.

However, important works remains to be done :

  • On Windows, it’s hard to install scikit-learn from pip (as pip stayed on python 2.x..), I need to find a good installation process to let the user use SVM, RF, or KNN algorithms. By default only Gaussian Mixture Model is available.
  • I must add the possibility to cancel treatment to stop the process of the training or predicting function.
  • Finish migrating every algorithms to the processing toolbox (especially Dynamic Time Warping), and more important, easier the way to implement them. Because lot of function have been developped during my thesis and it will be a nice thing to share them in this plugin.

Feel free to test and if you find some problems or have any ideas to improve dzetsaka, share it on dzetsaka/qgis3 issues page from Github.